© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55392
    Prev
    Next
    INDEX
    Explanations

    reporting past outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    likeidentities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ussa
    0.45
    近日
    0.44
    ための
    0.42
    最終
    0.42
    ny
    0.42
     för
    0.41
     déplacements
    0.41
    寧
    0.41
    颜值
    0.40
    ledovatel
    0.40
    POSITIVE LOGITS
     находя
    0.49
     entrando
    0.46
     levando
    0.45
    িশালী
    0.43
     кори
    0.43
     сфе
    0.43
    Multipart
    0.42
     avendo
    0.42
     употре
    0.41
     прода
    0.41
    Activations Density 0.001%

    No Known Activations